CN118253079A - Motion data processing method and system - Google Patents

Abstract

One or more embodiments of the present specification relate to a motion data processing method and system, the method including obtaining motion data of a user at an unsynchronized frequency, the motion data including at least an electromyographic signal; determining a physiological state of the user based on the motion data; and determining a recommended stride frequency of the user based on the physiological state.

Description

Motion data processing method and system

Technical Field

The present disclosure relates to the field of data acquisition and processing technologies, and in particular, to a method and a system for processing motion data.

Background

With the attention of people to physical health, scientific running is becoming more and more important. The step frequency and the stride length during running can be used for measuring whether the running of people is scientific or not. In general, the stride length is closely related to the height, leg length, joint flexibility, core strength, etc., and the stride frequency is easier to change by training, thereby improving the exercise effect during running. Current methods of determining stride frequency typically use a standard stride frequency of a runner (e.g., 180 stride frequencies per minute) as a recommended stride frequency for the general population, and the stride frequency of a runner may not be suitable for each general population given the differences in physical quality from one general population to another and the differences in physical quality between general populations.

It is therefore particularly important how to determine the stride frequency appropriate for the user to assist the user in performing running exercises more safely and scientifically.

Disclosure of Invention

The embodiment of the specification provides a motion data processing method, which comprises the following steps: acquiring motion data of a user under asynchronous frequency, wherein the motion data at least comprises electromyographic signals; determining a physiological state of the user based on the motion data; and determining a recommended stride frequency of the user based on the physiological state. The physiological state of the user is determined according to the motion data of the user under the unsynchronized frequency, so that the recommended step frequency of the user is determined, and the recommended step frequency determined by the method can be more suitable for the user, so that the user can be helped to perform motion more safely and scientifically.

In some embodiments, the acquiring the motion data of the user at the unsynchronized frequency comprises: determining a target speed interval; and acquiring motion data in the asynchronous frequency in the target speed interval based on the target speed interval. By reasonably setting the range of the target speed interval, the influence of different movement speeds under asynchronous frequency on the acquired movement data can be reduced, so that the accuracy of the movement data is ensured.

In some embodiments, the physiological state includes muscle efficiency, muscle tension, and muscle fatigue, and the determining the recommended stride frequency of the user based on the physiological state includes: determining a correspondence between the physiological state of the user and a step frequency based on at least one of the muscle efficiency, the muscle tension, and the muscle fatigue; and determining the recommended step frequency of the user based on the corresponding relation. The recommended step frequency determined according to the mode is more suitable for the user, so that when the user runs under the recommended step frequency, the exercise efficiency of the user can be improved (for example, the muscle efficiency is in an optimal state, the muscle fatigue state and the tension degree are in a target interval), meanwhile, the exercise injury of the user can be prevented, and the scientificity and the safety of exercise are ensured.

In some embodiments, the determining the physiological state of the user based on the motion data comprises: at least one of the muscle efficiency, the muscle tension, and the muscle fatigue of the user is determined based on the electromyographic signal. The electromyographic signals can be used for determining whether the muscles of the user are in a fatigue state, muscle efficiency and muscle tension degree, and the physiological state of the user can be determined according to the electromyographic signals to more accurately reflect the current condition of the muscles of the user, so that the muscles are not damaged in the exercise process of the user.

In some embodiments, the motion data includes electrocardiographic and/or gestural signals, the determining a recommended stride frequency of the user based on the physiological state includes: based on the electrocardiosignal and/or the gesture signal, determining a corresponding relation between the physiological state and step frequency of the user; and determining the recommended step frequency of the user based on the corresponding relation. The recommended step frequency determined according to the electrocardiosignal and/or the gesture signal can be more suitable for the user, so that when the user runs under the recommended step frequency, the exercise efficiency (for example, whether the running action is standard) can be further improved, meanwhile, the exercise damage of the user can be prevented, and the scientificity and the safety of the exercise are ensured.

In some embodiments, the determining the physiological state of the user based on the motion data comprises: a physiological state of the user is determined based on the electrocardiographic and/or posture signals, the physiological state comprising a risk of injury to the user's movement. The electrocardiosignal can be used for determining the heart injury risk of the user, the gesture signal can be used for representing the technical accuracy (such as joint angle, force sequence and the like) of the current movement of the user, and the physiological state of the user can be determined according to the electrocardiosignal and/or the gesture signal so as to more accurately reflect the current situation of the heart and/or the action gesture of the user, thereby ensuring the motion of the user to be safer.

In some embodiments, the acquiring motion data of the user at the unsynchronized frequency includes: acquiring real-time step frequency and real-time motion data of the user; dividing the real-time step frequency into a plurality of step frequency intervals; determining the motion data in an asynchronous frequency interval from the real-time motion data based on the step frequency interval; the real-time step frequency is obtained through an inertial sensor or is obtained from the electromyographic signals. The exercise data (i.e. the real-time exercise data) generated by running the user under different real-time stride frequency are different, the method for acquiring the exercise data based on the real-time stride frequency and the real-time exercise data can be free of controlling the stride frequency of the user, and the user can freely exercise with the asynchronous frequency, so that the exercise flexibility is higher.

In some embodiments, the method further comprises: and feeding back the recommended step frequency to the user. After the recommended step frequency of the user is determined, the recommended step frequency can be further fed back to the user, and the user can adjust the step frequency according to the recommended step frequency until the step frequency is the same as the recommended step frequency, so that the movement efficiency is improved.

In some embodiments, the feeding back the recommended step frequency to the user includes: acquiring the real-time step frequency of the user; determining a step frequency adjustment trend of the user based on the frequency difference between the real-time step frequency and the recommended step frequency; and guiding the user based on the step frequency adjustment trend until the step frequency of the user is the same as the recommended step frequency. The step frequency adjusting trend based mode for guiding the user to adjust the step frequency can enable the step frequency adjusting process of the user to be more scientific and healthy.

In some embodiments, the feeding back the recommended step frequency to the user includes: feeding back beats which are the same as the recommended step frequency to the user based on a preset feedback mode; the preset feedback mode comprises at least one of voice feedback, vibration feedback, lamplight feedback and display feedback. Based on a preset feedback mode, the dynamic beat with gradually changing frequency is fed back to the user, so that the user can adjust the self step frequency according to the frequency change trend of the dynamic beat, and the step frequency adjusting process is more scientific and reasonable.

In some embodiments, the feeding back the recommended step frequency to the user includes: and stimulating the body part of the user based on a biofeedback mode to feed back the recommended step frequency to the user, wherein the stimulation has a stimulation frequency which is the same as the recommended step frequency. The recommended step frequency is fed back to the user in a biofeedback mode, so that the user is more sensitive to the perception of the recommended step frequency, and the step frequency is adjusted more accurately.

In some embodiments, the acquiring motion data of the user at the unsynchronized frequency includes: and acquiring multiple sets of motion data of the user under multiple preset step frequencies, wherein each set of motion data corresponds to one of the multiple preset step frequencies. The motion data under different preset step frequencies may be different, and by respectively corresponding each of the plurality of sets of motion data under the plurality of preset step frequencies to one of the plurality of preset step frequencies, the accuracy of the motion data can be improved.

In some embodiments, the acquiring the plurality of sets of motion data of the user at a plurality of preset step frequencies includes: acquiring physiological information of the user, wherein the physiological information comprises body information and motion information; and determining the plurality of sets of motion data of the user at the plurality of preset step frequencies based on the physiological information. The motion data of users with different physiological information under the same preset step frequency can be different, the physiological information of the users can influence the motion data generated by the users in the motion process, and multiple groups of motion data of the users under multiple preset step frequencies are determined based on the physiological information, so that the motion data is more accurate.

Embodiments of the present disclosure also provide a athletic data processing system, including: the acquisition module is used for acquiring motion data of a user under asynchronous frequency, wherein the motion data at least comprises an electromyographic signal; a processing module for determining a physiological state of the user based on the motion data; and the recommending module is used for determining the recommending step frequency of the user based on the physiological state.

The embodiments of the present specification also provide a wearable device, including: the wearable device comprises a wearable body, wherein the wearable body is provided with at least one sensor, and the sensor is used for acquiring motion data of a user; and a processor configured to perform the method of motion data processing described in any of the embodiments of the present specification.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is an exemplary scenario diagram of a athletic data processing system shown according to some embodiments of the present disclosure;

FIG. 2 is an exemplary block diagram of an athletic data processing device, according to some embodiments of the present disclosure;

FIG. 3 is an exemplary flow chart of a method of motion data processing according to some embodiments of the present description;

FIG. 4 is an exemplary flow chart of a method of acquiring athletic data, according to some embodiments of the disclosure;

FIG. 5 is an exemplary flow chart for determining recommended stride frequency according to some embodiments of the present disclosure;

FIG. 6 is an exemplary flow chart of a feedback recommended stride method according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

FIG. 1 is an exemplary scenario diagram of a athletic data processing system according to some embodiments of the specification. As shown in fig. 1, athletic data processing system 100 may include a processing device 110, a network 120, a storage device 130, a terminal device 140, and a data collection apparatus 150. The various components in motion data processing system 100 may be connected in a variety of ways. For example, the data acquisition device 150 may be connected to the storage device 130 and/or the processing device 110 through the network 120, or may be directly connected to the storage device 130 and/or the processing device 110. For another example, the storage device 130 may be directly connected to the processing device 110 or connected through the network 120. For another example, terminal device 140 may be coupled to storage device 130 and/or processing device 110 via network 120, or may be coupled directly to storage device 130 and/or processing device 110. In some embodiments, the athletic data processing system 100 may also include a wearable device 160, with the data collection device 150 disposed on the wearable device 160 (e.g., the coat 160-1, the pants 160-2, the waistband 160-3). Wearable device 160 is connected to various components in athletic data processing system 100 through data collection device 150.

In some embodiments, athletic data processing system 100 may determine the recommended stride frequency when the user is running by implementing the methods and/or processes disclosed in this specification. For example, while the user is running wearing the wearable device 160, the data acquisition device 150 can be fitted on the skin of the human body to acquire motion data of the user while running, and the processing device 110 can directly or indirectly acquire the motion data (e.g., electromyographic signals, posture signals, electrocardiographic signals, etc.) from the data acquisition device 150 and determine the physiological state of the user from the motion data, thereby determining the recommended step frequency of the user while running.

Processing device 110 may process data and/or information obtained from data acquisition apparatus 150, storage device 130, terminal device 140, and/or other components of motion data processing system 100. In some embodiments, the processing device 110 may obtain the user's athletic data from any one or more of the data collection device 150, the storage device 130, or the terminal device 140, and determine the user's recommended stride frequency by processing the athletic data. In some embodiments, processing device 110 may retrieve pre-stored computer instructions from storage device 130 and execute the computer instructions to implement the methods of athletic data processing described herein.

In some embodiments, the processing device 110 may be a single server or a group of servers. The server farm may be centralized or distributed. In some embodiments, the processing device 110 may be local or remote. For example, the processing device 110 may access information and/or data from the data acquisition device 150, the storage device 130, and/or the terminal device 140 via the network 120. As another example, the processing device 110 may be directly connected to the data acquisition apparatus 150, the storage device 130, and/or the terminal device 140 to access information and/or data. In some embodiments, the processing device 110 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

Network 120 may connect various components of athletic data processing system 100 and/or connect athletic data processing system 100 with external resource portions. Network 120 may enable communication between various components of athletic data processing system 100, as well as other portions of athletic data processing system 100, to facilitate the exchange of data and/or information. For example, processing device 110 may obtain motion data from data acquisition apparatus 150 and/or storage device 130 via network 120. For another example, the processing device 110 may control the terminal device 140 to feed back recommended step frequencies to the user via the network 120. Exemplary feedback means may include at least one of voice feedback, vibration feedback, light feedback, display feedback, and the like.

In some embodiments, network 120 may be any form of wired or wireless network, or any combination thereof. By way of example only, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, and the like, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points, such as base station and/or Internet switching points 120-1, 120-2, …, through which one or more components of motion data processing system 100 may be connected to network 120 to exchange data and/or information. For example, movement data, physiological status of the user, etc. data may be communicated over the network 120.

Storage device 130 may store data, instructions, and/or any other information. In some embodiments, the storage device 130 may store data obtained from the data acquisition apparatus 150, the processing device 110, and/or the terminal device 140. For example, the storage device 130 may store motion data acquired by the data acquisition apparatus 150. In some embodiments, storage device 130 may store data and/or instructions that processing device 110 uses to perform or use to implement the exemplary methods described in this specification. In some embodiments, the storage device 130 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, storage device 130 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

In some embodiments, storage device 130 may be connected to network 120 to communicate with at least one other component (e.g., data acquisition apparatus 150, processing device 110, terminal device 140) in athletic data processing system 100. At least one component of athletic data processing system 100 may access data, instructions, or other information stored in storage device 130 over network 120. In some embodiments, storage device 130 may be directly connected to or in communication with one or more components (e.g., data acquisition apparatus 150, terminal device 140) in motion data processing system 100. In some embodiments, the storage device 130 may be part of the data acquisition apparatus 150 and/or the processing device 110.

Terminal device 140 may receive, transmit, and/or display data. The data received by the terminal device 140 may include data collected by the data collection device 150, data stored by the storage device 130, recommended step frequencies generated by the processing device 110, and so on. For example, the data received and/or displayed by the terminal device 140 may include movement data collected by the data collection device 150, physiological state data of the user obtained by processing the movement data by the processing device 110, recommended step frequency determined by the processing device 110 based on the physiological state, and so on. The data transmitted by the terminal device 140 may include input data and instructions of the user, etc. For example, the terminal device 140 may send an operation instruction input by the user to the data acquisition device 150 through the network 120, so as to control the data acquisition device 150 to perform corresponding data acquisition (such as electromyographic signals, electrocardiographic signals, gesture signals, and the like).

In some embodiments, terminal device 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, or the like, or any combination thereof. In some embodiments, the mobile device 141 may include a cell phone, smart mobile device, virtual reality device, augmented reality device, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smart phone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a POS device, etc., or any combination thereof. In some embodiments, the metaverse device and/or augmented reality device may include a metaverse helmet, metaverse glasses, metaverse eyepieces, augmented reality helmets, augmented reality glasses, augmented reality eyepieces, and the like, or any combination thereof. In some embodiments, the processing device 110 may be part of the terminal device 140.

It should be noted that the athletic data processing system 100 may not include the terminal device 140, and the functions or portions of the functions of the terminal device 140 may be performed by the wearable device 160. For example, the data acquisition device 150 may be controlled by the wearable apparatus 160 for corresponding data acquisition. For another example, data displayed to the user by the terminal device 140 (e.g., recommended stride frequency) may be performed by the wearable device 160 (e.g., the wearable device 160 feeds back the recommended stride frequency to the user in an electrically stimulated manner).

The data acquisition device 150 may be a device that performs motion data acquisition for a user. The motion data may refer to signals generated by the user during running. Exemplary motion data may include one or more of electromyographic signals, posture signals, electrocardiographic signals, respiratory signals, sweat signals, mechanical signals, and the like. In some embodiments, the data acquisition device 150 may include an myoelectric data acquisition device, a posture data acquisition device, and a mechanical data acquisition device. In some embodiments, the myoelectric data acquisition device may include one or more electrodes. For example, the myoelectric data acquisition device may include a plurality of electrodes that may be provided at different locations of the wearable apparatus 160 for engaging with different locations of the user (e.g., chest, back, elbow, leg, abdomen, wrist, etc.) to acquire myoelectric signals at different locations of the user. In some embodiments, the gesture data acquisition device may include a speed sensor, an inertial sensor (e.g., an acceleration sensor, an angular velocity sensor (e.g., a gyroscope), etc.), an optical sensor (e.g., an optical distance sensor, a video/image acquisition device), an acoustic distance sensor, a tension sensor, etc., or any combination thereof. In some embodiments, the mechanical data acquisition device may include a pressure sensor. For example, pressure sensors may be provided at different locations of the user to collect pressure signals at different locations. In some embodiments, the data acquisition device 150 may also include an electrocardiographic data acquisition device, a respiratory data acquisition device, a sweat data acquisition device, and the like. For example, the electrocardiographic data acquisition device may include a plurality of electrodes that may be used to engage different portions of the user (e.g., by the waistband device 160-3 engaging the abdomen) to acquire electrocardiographic signals of the user. For another example, the respiratory data acquisition device may include a respiratory rate sensor, a flow sensor, etc. for detecting signals of respiratory rate, gas flow, etc. of the user during the movement, respectively. As another example, the sweat data collection device may include a plurality of electrodes in contact with the user's skin for detecting the user's sweat flow, analyzing sweat components, and the like. In some embodiments, the data acquisition device 150 may have a separate power source that may send acquired data to other components (e.g., the processing device 110, the storage device 130, the terminal device 140) by wired or wireless means (e.g., bluetooth, wiFi, etc.).

Wearable device 160 refers to a garment or device having a wearable function. In some embodiments, wearable device 160 may include, but is not limited to, a coat apparatus 160-1, a pants apparatus 160-2, a waistband apparatus 160-3, shoes 160-4, and the like. In some embodiments, one or more data acquisition devices 150 may be provided in the wearable apparatus 160 to acquire movement data for different locations. When the user wears the wearable device 160 to move, the data collection device 150 may contact with a body part of the user, thereby collecting movement data. For example, the data acquisition device 150 (e.g., electrodes) on the wearable apparatus 160 may be in contact with multiple sites of the human body, e.g., the lower leg, thigh, buttocks, waist, chest, shoulders, etc., to acquire electromyographic signals of the sites. For another example, the data acquisition device 150 (e.g., inertial sensor) on the wearable device 160 may be in contact with multiple limbs (e.g., thigh, forearm, thigh, shank, etc.) or joint locations (e.g., knee, ankle, elbow, etc.) of the human body to acquire pose signals of the respective locations. In some embodiments, the coat device 160-1, the pants device 160-2, the waistband device 160-3, the shoes 160-4, and the like may be configured as a wearing body of the wearable device 160, and the data acquisition device 150 is disposed on the wearing body.

It should be noted that the wearing body of the wearable device 160 is not limited to the coat device 160-1, the pants device 160-2, the waistband device 160-3 and the shoe device 160-4 shown in fig. 1, but may also include other devices, such as a wrist ring device, a glove device, etc., which are not particularly limited herein. It is understood that the user wearing wearable device 160 for running exercises may be a runner, an exercise device tester, etc. The number of users may be one or more.

The description of athletic data processing system 100 is intended to be illustrative, and not limiting of the scope of the present description. Many alternatives, modifications, and variations will be apparent to those skilled in the art. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. Such modifications are intended to fall within the scope of this specification.

Fig. 2 is an exemplary block diagram of a motion data processing apparatus according to some embodiments of the present description. In some embodiments, the athletic data processing device 200 shown in FIG. 2 may be applied to the athletic data processing system 100 shown in FIG. 1 in software and/or hardware, e.g., may be configured in software and/or hardware to the processing device 130 and/or the terminal device 140 for determining a recommended stride frequency for the user based on the user's athletic data. In some embodiments, the athletic data processing device 200 may include an acquisition module 210, a processing module 220, a recommendation module 230, and a feedback module 240.

The acquisition module 210 may be configured to acquire motion data of the user at an unsynchronized frequency. For example, the acquisition module 210 may acquire motion data from any one or more of the signal acquisition device 150, the storage device 130, or the terminal device 140. In some embodiments, the motion data may include electromyographic signals, posture signals, electrocardiographic signals, respiratory signals, sweat signals, mechanical signals, and the like.

The processing module 220 may be configured to determine a physiological state of the user based on the motion data. In some embodiments, the physiological state may include muscle efficiency, muscle tension, muscle fatigue, risk of athletic injury, and the like. In some embodiments, the processing module 220 may determine at least one of muscle efficiency, muscle tension, and muscle fatigue of the user from the electromyographic signals, thereby determining the physiological state of the user. In some embodiments, the processing module 220 may determine a risk of injury to the user's motion from the electrocardiographic signals and/or the gesture signals, thereby determining a physiological state of the user.

The recommendation module 230 may be used to determine recommended stride frequencies for the user based on the physiological state. In some embodiments, the recommendation module 230 may determine a recommended stride frequency for the user based on a correspondence between the physiological state of the user and the stride frequency. For example, the recommendation module 230 may determine the recommended stride frequency based on the correspondence between muscle efficiency, muscle tension, and muscle fatigue and stride frequency. For another example, the recommendation module 230 may determine a recommended stride frequency based on a correspondence between the risk of athletic injury and the stride frequency.

The feedback module 240 may be used to feedback recommended stride frequency to the user. In some embodiments, the feedback module 240 may feedback the same beat as the frequency of the recommended step frequency to the user based on a preset feedback manner (e.g., voice feedback, vibration feedback, etc.). In some embodiments, the feedback module 240 may direct the user to adjust the stride frequency based on the user's real-time stride frequency until the user's stride frequency is the same as the recommended stride frequency. In some embodiments, the feedback mode of feedback module 240 may be real-time feedback. The user may view or receive the feedback results in real time through a terminal device (e.g., a cell phone, a watch). In some embodiments, the feedback mode of feedback module 240 may also be non-real time feedback. The user can view the statistics of the sports situation generated after the sports through the terminal equipment (such as a mobile phone, a watch and a computer). In some embodiments, the feedback module 240 is configured to feedback the recommended step frequency to the user, and the feedback module 240 may be omitted and the feedback function performed by components of other modules (e.g., the acquisition module 210). For more details on the various modules of the athletic data processing device 200, reference may be made to FIGS. 3-6 and the associated descriptions herein.

It should be noted that the above description of the athletic data processing device 200 and its modules is for convenience only and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that having the benefit of the teachings of the apparatus and/or modules, it is possible to combine individual modules arbitrarily or to construct sub-modules in connection with other modules without departing from the teachings. For example, the feedback module 240 may be omitted or replaced with other devices or modules, and the like, variations of which are within the scope of the present description.

Fig. 3 is an exemplary flow chart of a method of motion data processing according to some embodiments of the present description. In some embodiments, the process 300 may be performed by processing logic that may comprise hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (instructions run on a processing device to perform hardware simulation), or the like, or any combination thereof. In some embodiments, one or more operations in flow 300 of the athletic data processing method shown in FIG. 3 may be implemented by processing device 110 and/or terminal device 140 shown in FIG. 1. For example, the flow 300 may be stored in the storage device 130 in the form of instructions and executed by the processing device 110 and/or the terminal device 140 to invoke and/or execute. As shown in fig. 3, the process 300 may include:

in step 310, motion data of the user at an unsynchronized frequency is obtained, wherein the motion data at least comprises an electromyographic signal.

In some embodiments, step 310 may be performed by the acquisition module 210. In some embodiments, the athletic data may be data generated by the user during running. The athletic data may be used to characterize a state (e.g., physiological state) of the user during running. In some embodiments, the motion data may include electromyographic signals. The electromyographic signal may be a bioelectric signal generated by a muscle during exercise. The electromyographic signals may be used to determine the physiological state of the user during running (e.g., muscle efficiency, muscle tension). In some embodiments, the electromyographic signals may be acquired by a data acquisition device (e.g., one or more electrodes) that is attached to the user while the user is wearing the wearable device. For example, one or more electrodes may be applied to muscles of different parts of the user (e.g., thigh, calf, waist, buttocks) to collect electromyographic signals of the corresponding muscle parts.

In some embodiments, the motion data may also include an attitude signal and an electrocardiographic signal. The posture signal may include information such as an angle, a speed, and an acceleration of each joint, or an euler angle, an angular speed, and an angular acceleration of each human body part. In some embodiments, the gesture signal may be used to characterize a physiological state of a current motion of the user (e.g., risk of athletic injury). In some embodiments, the gesture signal may be acquired by a data acquisition device (e.g., gesture signal acquisition device). Exemplary gesture signal acquisition devices may include a speed sensor, an inertial sensor (e.g., acceleration sensor, angular velocity sensor (e.g., gyroscope), etc.), an optical sensor (e.g., optical distance sensor, video/image acquisition), an acoustic distance sensor, a tension sensor, etc., or any combination thereof. An electrocardiograph signal may refer to a signal that is used to represent the condition of heart activity of a user. In some embodiments, the electrocardiograph signal may be acquired by an electrocardiograph signal acquisition device. For example, the electrocardiographic signal acquisition device may include a plurality of electrodes that may be used to conform to different portions of the user, such as the abdomen, to acquire electrocardiographic signals of the subject under evaluation. For more details on the posture signal and the electrocardiographic signal, reference may be made to fig. 5 and its related description of the embodiments of the present specification.

In other embodiments, the motion data may also include respiratory signals, mechanical signals, sweat signals, and the like, or any combination thereof. The respiration signal may refer to a signal representing the respiration of the user. In some embodiments, the respiratory signal may be acquired by a respiratory signal acquisition device. For example, the respiratory signal acquisition device may include a respiratory rate sensor, a flow sensor, etc. for detecting data of respiratory rate, gas flow, etc. of the subject to be evaluated during the movement, respectively. Sweat signals may refer to signals that are used to represent the sweating of a user. In some embodiments, sweat signals may be acquired by a sweat signal acquisition device. For example, the sweat signal acquisition device may include a plurality of electrodes in contact with the skin of the user for detecting sweat flow of the user or analyzing sweat components, etc. The mechanical signal may refer to a corresponding force at a joint portion of the user, and the mechanical signal may be used to characterize a risk of athletic injury to the user (e.g., ankle pressure, knee pressure, etc.). In some embodiments, the mechanical signal may be obtained by a mechanical sensor. For example, the mechanical sensor may include a pressure sensor, and the pressure signals of different parts of the user may be obtained as mechanical signals of the user based on the pressure sensor. In some embodiments, the mechanical signal may be calculated based on the gesture signal and the electromyographic signal. In some embodiments, the electromyographic signals, cardiac signals, posture signals, respiratory signals, sweat signals, etc., or any combination thereof, may be used to characterize the physiological state of the user during running (e.g., muscle efficiency, muscle fatigue state, risk of athletic injury, etc.).

In some embodiments, the processing device 110 may acquire the motion data directly from a data acquisition device (e.g., the data acquisition device 150). In some embodiments, the motion data may be stored in a storage device (e.g., storage device 130) from which the processing device 110 may retrieve the motion data.

In some embodiments, multiple sets of motion data for a user at multiple preset step frequencies may be acquired. Each of the plurality of preset step frequencies may be located in a specific frequency range (also referred to as a step number range), and each of the plurality of sets of motion data corresponds to one of the plurality of preset step frequencies, respectively. In some embodiments, the stride frequency may be the number of steps that are run per unit time (e.g., per minute). By way of example only, the stride frequency of a professional runner may be approximately 180 steps per minute. In some embodiments, each preset step frequency may be a preset step frequency located in a specific frequency range. The frequency ranges corresponding to the plurality of preset step frequencies are different from each other. In some embodiments, the frequency range of the preset step frequency may be set by default. In some embodiments, the frequency range of the preset step frequency may also be set individually according to the situation of different users. The set preset step frequency and/or its corresponding frequency range may be stored in a storage device. In some embodiments, the plurality of preset step frequencies may include a first preset step frequency, a second preset step frequency, … …, an nth preset step frequency, the first preset step frequency, the second preset step frequency, … …, the nth preset step frequency corresponding to different frequency ranges. For example only, the first preset step frequency may be in or correspond to a frequency range of 100 steps per minute to 110 steps per minute, the second preset step frequency may be in or correspond to a frequency range of 110 steps per minute to 120 steps per minute, …, and the nth preset step frequency may be in or correspond to a frequency range of 180 steps per minute to 190 steps per minute. In some embodiments, motion data at each of a plurality of preset stride frequencies may be acquired separately.

In some embodiments, multiple sets of athletic data at multiple preset stride frequencies may be acquired during a user's running. For example, when a user runs at a first preset stride frequency, first exercise data of the user at the first preset stride frequency may be obtained; then, the user adjusts the step frequency to a second preset step frequency, and second motion data at the second preset step frequency is obtained … …, and similarly, nth motion data of the user at the nth preset step frequency can be obtained. In some embodiments, multiple sets of motion data at different preset stride frequencies may also be obtained from a user's historical motion record (e.g., stride frequency record, motion data record corresponding to stride frequency record). In some embodiments, each of the plurality of sets of motion data may characterize a physiological state of the user at a corresponding preset stride frequency.

In some embodiments, the preset stride frequency may be fed back to the user by feedback means (e.g., voice means, vibration means, etc.) so that the user follows the preset stride frequency to generate movement data at the preset stride frequency. For example, the preset step frequency can be fed back to the user in a voice mode, the wearable device or the terminal device (such as a mobile phone) can play a voice rhythm, the frequency of the voice rhythm is the same as that of the preset step frequency, the user runs along with the voice rhythm, and the data acquisition device is used for acquiring the movement data of the user during running. The motion data is the motion data generated under the preset step frequency.

In some embodiments, obtaining multiple sets of motion data for a user at multiple preset step frequencies may include: and acquiring physiological information of the user, and determining multiple groups of motion data of the user under multiple preset step frequencies based on the physiological information. In some embodiments, the physiological information of the user may include physical information and movement information. The physical information refers to information related to physical conditions or physical characteristics of the user. In some embodiments, the body information may include, but is not limited to, one or more of gender, age, height, weight, body composition information, and the like. For example only, the body composition information may include body fat rate, muscle mass, skeletal muscle rate, bone mass, subcutaneous fat, body moisture, and the like. The motion information refers to information related to a user's historical motion. The athletic information may include athletic habits, athletic performance, and the like. For example only, the exercise habits may include, but are not limited to, exercise frequency, exercise type, exercise duration, and the like. Physiological information corresponding to different users may be stored in the storage device. In some embodiments, physiological information of different users (e.g., as testers acquiring multiple sets of athletic data) may be collected in advance and stored in a storage device. When multiple sets of motion data of the user under multiple preset step frequencies are acquired, physiological information of the user can be acquired from the storage device, and multiple sets of motion data of the user under multiple preset step frequencies are determined based on the physiological information of the user. For example, the test person may include user 1, user 2, …, and physiological information for each of the user m, m users is stored in the storage device. When acquiring multiple sets of motion data of the user 1 at multiple preset step frequencies, physiological data of the user 1 may be acquired from the storage device, and multiple sets of motion data (e.g., electromyographic signals, gesture signals, electrocardiosignals, etc.) of the user 1 at different preset step frequencies may be determined based on the physiological data of the user 1. In a similar manner, multiple sets of motion data for different users (i.e., users with different physiological information) at different preset stride frequencies may be determined separately. In some embodiments, the exercise data of the users with different physiological information at the same preset step frequency may be different, and the physiological information of the users may affect the exercise data generated by the users during the exercise, thereby affecting the physiological state of the users. In some embodiments, the relationship between the user's step frequency and physiological state under different conditions (e.g., physiological information is different) may be determined from the physiological information of the user, as described elsewhere in this specification (e.g., step 330).

In some embodiments, the motion data of the user under the unsynchronized frequency may be obtained based on other manners, for example, the real-time motion data of the user may be obtained based on the real-time step frequency of the user, and the specific content may be seen in fig. 4 and related description.

In some embodiments, the user's movement speed is related to a stride frequency, which may be an indicator of the speed of movement being evaluated. In general, the speed of motion may be expressed approximately as the product of the stride frequency and the stride length. Therefore, when the motion speed of the user is kept stable (i.e. uniform motion or near uniform motion) or is located in a certain range, the motion data of the user is acquired in the current speed or speed range, and the acquired motion data can be used as a relatively stable measurement standard to determine the step frequency. In some embodiments, acquiring motion data of the user at the unsynchronized frequency may include: determining a target speed interval; and acquiring motion data in the asynchronous frequency in the target speed interval based on the target speed interval.

The speed interval may be a range of values for running speed during the user's exercise. The target speed zone is a preset speed zone having a certain speed range. In some embodiments, the speed range defined by the target speed interval may be smaller, i.e., the change in running speed is smaller within the target speed interval. When the movement speed of the user is kept within the target speed interval, the movement data acquired based on the target speed interval can be used as a relatively stable measurement to determine the step frequency. As an exemplary description only, the user moves at a first preset step frequency within the target speed interval, and the motion data acquired at this time is first motion data; the user moves in a target speed interval with a second preset step frequency, and the acquired motion data are second motion data; … …; the user moves in the target speed interval with the N preset step frequency, and the acquired motion data is the N motion data. The influence factors of the differences among the first motion data, the second motion data and … … and the Nth motion data are mainly step frequencies, and the motion speed is negligible. In some embodiments, when the movement speed of the user is within the target speed interval, the user moves at a preset step frequency, and the movement data acquired by the data acquisition device is valid, and the movement data corresponds to the preset step frequency and can be used for subsequent analysis processing (for example, for determining the physiological state of the user). When the movement speed of the user exceeds the target speed interval, the data acquisition device does not acquire movement data no matter whether the user moves at a preset step frequency or not, or the acquired movement data are invalid, and the invalid movement data are not used for subsequent analysis and processing. In some embodiments, an appropriate target speed interval may be set according to actual situations (for example, different users, road environments) and application scenarios, and the range of the target speed interval is not specifically limited in this specification.

By reasonably setting the range of the target speed interval, the influence of different movement speeds under asynchronous frequency on the acquired movement data can be reduced, so that the accuracy of the movement data is ensured.

In some embodiments, to reduce the difference in motion data caused by the difference in motion speed at the unsynchronized frequency, the motion data of the user at the unsynchronized frequency but at the same motion speed may be obtained. In some embodiments, the user's motion data at different motion speeds and at different frequencies may be obtained, in which case the effects of the different motion speeds may be compensated for by monitoring the user's motion speed and in the result of the motion data.

Step 320, determining a physiological state of the user based on the motion data.

In some embodiments, step 320 may be performed by processing module 220. In some embodiments, the physiological state may be used to characterize the physiological condition and its changing state during the running of the user. In some embodiments, the physiological state may include muscle efficiency, muscle fatigue (also referred to as a muscle fatigue state), and muscle tension. In some embodiments, the user may vary in muscle efficiency, muscle fatigue, and muscle tension during running at an unsynchronized frequency, resulting in different athletic efficiencies (e.g., running performance, fitness effects, etc.) for the user. In some embodiments, the physiological state of the user may be determined from the electromyographic signals. For example, the physiological state of the user may be determined from the characteristic value of the electromyographic signal. The characteristic value of the electromyographic signal may be a characteristic parameter of the electromyographic signal that represents the physiological state of the user. Exemplary characteristic parameters may include the magnitude of the electromyographic signal, the absolute value of the magnitude, the average value of the magnitude (or absolute value), the maximum value, the minimum value, the median frequency, the peak frequency, the total force, the electromyographic power, the foot strike time, the average frequency, and the like.

In some embodiments, it may be determined whether the user's muscles are in a tired state based on the electromyographic signals in the motion data. For example, the total force exerted by leg muscles in a fatigued state is greater than the total force exerted by leg muscles in a non-fatigued state. The total force may be characterized by a sum of magnitudes of the electromyographic signals (e.g., a sum of absolute magnitudes, a sum of multiples of magnitudes, etc.) over a preset period of time (e.g., one running cycle, a period of foot contact, a period of foot vacation, etc.). At this time, the sum of the magnitudes of the electromyographic signals as a characteristic parameter may be used to determine whether the muscles of the user are in a fatigued state. For another example, the myoelectric power of the leg muscle in the fatigued state is greater than the myoelectric power of the leg muscle in the non-fatigued state. Myoelectric power may refer to the sum of the magnitudes of the myoelectric signals per unit time. At this time, the myoelectric power of the myoelectric signal as a characteristic parameter may be used to determine whether the muscle of the user is in a tired state. For another example, in a non-tired state, a portion of the leg muscles relax as the legs are emptied, and the amplitude of the corresponding electromyographic signal may be a minimum over a period; and when the fatigue state is entered, the leg muscles are in a contracted state when the legs are emptied, for example, the muscle may be represented by an increase in the magnitude of the electromyographic signal when the legs are emptied. At this time, the amplitude of the electromyographic signal of the leg muscle when the leg is emptied can be used as a characteristic parameter to determine whether the muscle of the user is in a tired state. for another example, in a non-tired state, a portion of leg muscles tighten when the foot touches the ground, and the amplitude of the corresponding electromyographic signal may be a maximum value within one cycle; and when the leg muscle enters a fatigue state, the muscle strength of the leg muscle is abnormally increased when the foot touches the ground, for example, the amplitude increasing speed of the electromyographic signal is larger than a speed threshold value. At this time, the rate of rise of the magnitude of the electromyographic signal of the leg muscle when the foot touches the ground can be used as a characteristic parameter to determine whether the muscle of the user is in a tired state. For another example, when the leg muscles enter a fatigue state from a non-fatigue state, the average frequency, median frequency, or the like of the leg muscles decreases. The average frequency may be a ratio of the magnitude of the finger electromyographic signal at each frequency weighted (e.g., the magnitude at each frequency multiplied by the corresponding frequency, the multiple of the magnitude at each frequency, etc.) and summed to the sum of the magnitudes at each frequency. at this time, the average frequency of the electromyographic signals as a characteristic parameter may be used to determine whether the muscles of the user are in a fatigued state. For another example, the muscle strength of the leg muscles in the fatigued state is greater than the muscle strength in the non-fatigued state when the same running motion is performed. And as the degree of fatigue increases, the muscle strength further increases. When the muscle strength is excessive, leg muscles may be damaged due to excessive fatigue. Thus, the fatigue state of the muscle can be judged based on the intensity change of the electromyographic signal. Specifically, the electromyographic signals may be segmented according to a plurality of time windows divided by time periods, and the average value of the amplitude (for example, the absolute value of the amplitude) of each segment of the electromyographic signals is taken as the characteristic value of each segment of the electromyographic signals, thereby determining a plurality of characteristic values in a plurality of time periods. The average value of the amplitude value can reflect the average intensity of each section of the electromyographic signal in each time period in general, so that the change of the average intensity of the electromyographic signal in the running process can be judged based on a plurality of characteristic values, and the fatigue state of the muscle can be represented.

As the running time increases, the leg muscles gradually enter a fatigue state, and the muscle efficiency gradually decreases. Muscle efficiency may refer to the muscle output required to maintain the same motor capacity. In some embodiments, the higher the muscle output required to maintain the same motor capacity, the lower the muscle efficiency. In some embodiments, muscle efficiency may be determined from an integrated value of the electromyographic signal over a certain interval (e.g., over a certain period of time). In some embodiments, muscle efficiency may also be determined from an average of the magnitude of the electromyographic signal over a certain interval.

In some embodiments, the degree of tension of the user's muscles may be determined based on the electromyographic signals. The degree of muscle tension may refer to the degree of muscle relaxation during exercise. During running of the user, the leg muscles may be in periodic motion, wherein when the leg is emptied, a portion of the leg muscles (e.g., calf muscles) relax, and the amplitude of the corresponding electromyographic signal may be a minimum over a period; while when the leg (i.e., foot) touches the ground, a portion of the leg muscles contract, the amplitude of the corresponding electromyographic signal may be a maximum value within one cycle. Thus, the stress condition of the leg muscle can be judged based on the amplitude (e.g., minimum value, maximum value) of the electromyographic signal as a characteristic parameter, thereby determining the tension state of the leg muscle. For example, the electromyographic signals may be segmented according to a plurality of time windows divided by time periods, and a minimum value of the amplitude (for example, an absolute value of the amplitude) of each segment of the electromyographic signals is taken as a characteristic value of each segment of the electromyographic signals, thereby determining a plurality of characteristic values in a plurality of time periods. The minimum amplitude value can reflect the minimum intensity of each segment of the electromyographic signal in each time period, so that the change of the minimum intensity of the electromyographic signal in the running process can be judged based on a plurality of characteristic values, and the muscle tension degree can be represented by the minimum amplitude value.

Step 330, determining a recommended stride frequency of the user based on the physiological state.

In some embodiments, step 330 may be performed by recommendation module 230. In some embodiments, the user's muscle fatigue, muscle efficiency, and muscle tension are different when running at an unsynchronized frequency, which may cause the user's exercise efficiency to be different. The correspondence between the physiological state of the user and the stride frequency may be determined based on at least one of muscle efficiency, muscle tension, and fatigue state, and the recommended stride frequency of the user may be determined based on the correspondence. When running under the recommended step frequency, the exercise efficiency of the user can be improved (for example, the muscle efficiency is in an optimal state, the muscle fatigue state and the tension degree are in a target interval), meanwhile, the exercise injury of the user can be prevented, and the scientificity and the safety of the exercise are ensured.

In some embodiments, the correspondence between the physiological state of the user and the stride frequency, which is determined based on muscle fatigue, muscle efficiency, and/or muscle tension, may also be referred to as a first correspondence. In some embodiments, the first correspondence may include a correspondence between muscle efficiency and stride frequency. In some embodiments, a correspondence between muscle efficiency and a plurality of preset step frequencies may be determined. In some embodiments, the myoelectric signal at the first preset step frequency may be analyzed (e.g., calculated by using a feature value) to obtain the muscle efficiency (denoted as the first muscle efficiency) at the first preset step frequency, so as to determine the correspondence between the first preset step frequency and the first muscle efficiency. That is, the first muscle efficiency corresponds to a first preset stride frequency. Similarly, a correspondence between the second preset step frequency and the second muscle efficiency, a correspondence between the third preset step frequency and the third muscle efficiency, … …, and a correspondence between the nth preset step frequency and the nth muscle efficiency may be determined. In some embodiments, the correspondence between muscle efficiency and real-time stride frequency may also be determined. In some embodiments, the real-time step frequency of the user and the real-time myoelectric signal corresponding to the real-time step frequency can be obtained, and the real-time myoelectric signal is analyzed and processed to obtain the real-time muscle efficiency under the real-time step frequency.

In some embodiments, the recommended stride frequency for the user may be determined based on a correspondence between muscle efficiency and stride frequency. In some embodiments, one or more stride frequencies may be determined from the asynchronous stride frequencies as recommended stride frequencies based on a correspondence between muscle efficiency and stride frequencies. For example, one or more of the corresponding asynchronous frequencies (e.g., a plurality of preset step frequencies) when the muscle efficiency is high (or the muscle fatigue status level is low) may be determined as the recommended step frequency.

In some embodiments, the first correspondence may include a correspondence between muscle tension and stride frequency. In some embodiments, a correspondence between the degree of muscle tension and a plurality of preset step frequencies may be determined. By way of example only, the electromyographic signals at the first preset stride frequency may be analyzed to obtain a degree of muscle tension (denoted as a first degree of muscle tension) at the first preset stride frequency, so as to determine a correspondence between the first preset stride frequency and the first degree of muscle tension. I.e. the first muscle tension corresponds to a first preset stride frequency. Similarly, a correspondence between the second preset stride frequency and the second muscle tension level, a correspondence between the third preset stride frequency and the third muscle tension level, … …, and a correspondence between the nth preset stride frequency and the nth muscle tension level may be determined. In some embodiments, the correspondence between muscle tension and real-time stride frequency may also be determined. In some embodiments, the real-time stride frequency of the user and the real-time myoelectric signal corresponding to the real-time stride frequency may be obtained, and the real-time muscle tension degree under the real-time stride frequency may be obtained by analyzing and processing the real-time myoelectric signal.

In some embodiments, the recommended stride frequency of the user may be determined based on a correspondence between muscle tension and stride frequency. In some embodiments, one or more stride frequencies may be determined from the asynchronous stride frequencies as recommended stride frequencies based on a correspondence between muscle tension and stride frequencies. For example, one or more of the unsynchronized frequencies (e.g., a plurality of preset step frequencies) corresponding to a high degree of muscle tension within the human body's tolerance range may be determined as the recommended step frequency.

In some embodiments, the first correspondence may include a correspondence between muscle fatigue and stride frequency. In some embodiments, a correspondence between muscle fatigue and a plurality of preset step frequencies may be determined. By way of example only, the electromyographic signals at the first preset step frequency may be analyzed to obtain muscle fatigue (denoted as a first muscle fatigue level) at the first preset step frequency, so as to determine a correspondence between the first preset step frequency and the first muscle fatigue. That is, the first muscle fatigue level corresponds to a first preset stride frequency. Similarly, a correspondence between the second preset stride frequency and the second muscle fatigue, … …, and a correspondence between the nth preset stride frequency and the nth muscle fatigue may be determined. In some embodiments, the correspondence between muscle fatigue and real-time stride frequency may also be determined. In some embodiments, the real-time step frequency of the user and the real-time myoelectric signal corresponding to the real-time step frequency can be obtained, and the real-time myoelectric signal is analyzed and processed to obtain the real-time muscle fatigue under the real-time step frequency.

In some embodiments, the recommended stride frequency of the user may be determined based on a correspondence between muscle fatigue and stride frequency. In some embodiments, one or more stride frequencies may be determined from the asynchronous stride frequencies as recommended stride frequencies based on a correspondence between muscle fatigue and stride frequencies. In some embodiments, the recommended stride frequency of the user may also be determined by comprehensively considering the correspondence between muscle efficiency and stride frequency, the correspondence between muscle tension and stride frequency, and the correspondence between muscle fatigue and stride frequency.

In some embodiments, the correspondence between the step frequency and the physiological state of the user may be determined according to a relationship determination model. In some embodiments, the input to the relationship determination model may include, but is not limited to, a step frequency. The output of the relationship model may be a correspondence between the step frequency and the physiological state (e.g., muscle fatigue, muscle tension, muscle efficiency, risk of athletic injury, etc.). In some embodiments, the relationship determination model may be a trained machine learning model. In some embodiments, the relationship determination model may be trained beforehand by the processing device and stored in the storage device, which the processing device may access to obtain the relationship determination model. In some embodiments, the machine learning model may include one or more of a linear classification model (LR), a support vector machine model (SVM), a naive bayes model (NB), a K-nearest neighbor model (KNN), a decision tree model (DT), an integrated model (RF/GDBT, etc.), and the like.

In some embodiments, the relationship determination model may be trained based on sample information. The sample information may include different preset stride frequencies for different users. In some embodiments, the step frequency is taken as sample information, and the physiological state of the user can be monitored while the step frequency is acquired. In some embodiments, the sample information may be labeled as the machine learning model is trained. For example, the body of the user when moving at a first preset stride frequency may exhibit a first physiological state, and the first preset stride frequency may be labeled as "the first preset stride frequency corresponds to the first physiological state"; the user's body exhibits a second physiological state when exercising at a second preset frequency, which may be marked as "the second preset frequency corresponds to the second physiological state". The physiological states corresponding to different preset step frequencies are different, and the labeled sample information (namely, labeled preset step frequencies) is used as the input of a machine learning model to train the machine learning model, so that a relation determination model can be obtained. The relationship between the corresponding step frequency and the physiological state may be output when the corresponding step frequency (which may include a real-time step frequency) is input in the relationship determination model.

In some embodiments, in order to improve the accuracy of the correspondence between the preset step frequency and the physiological state, the physiological information of the user may also be used as an input of the machine learning model to train the machine learning model. Therefore, the corresponding relation between the step frequency and the physiological state under different conditions (for example, physiological information is different) can be obtained, and further, the recommended step frequency of the user can be determined based on the corresponding relation, so that the recommended step frequency is more suitable for the user. In some embodiments, the recommended stride frequency (also called initial recommended stride frequency) under the target training task may be estimated according to the information actually input by the user, the user may first move with the initial recommended stride frequency, real-time motion data of the user may be collected during the motion process, and the motion control system may iteratively update the relationship determination model according to the real-time motion data, so that the relationship determination model outputs a corresponding relationship that is more in accordance with the actual requirement, and based on the corresponding relationship, the recommended stride frequency (that is, the recommended stride frequency updated after iteration) that is more in accordance with the real-time motion state of the user may be redetermined. In some embodiments, the exercise data processing system may collect more exercise data accumulated during the long-term exercise of the user, so that the recommended step frequency recommended by the exercise data processing system is more reasonable and more suitable for the exercise habit of the user.

In some embodiments, the physiological state of the user and the recommended step frequency may also be determined by other manners or methods, for example, the physiological state of the user and the recommended step frequency may be determined according to the electrocardiosignal and/or the gesture signal, and specific content may be found in fig. 5 and related description thereof. In some embodiments, the recommended stride frequency for the user may be determined based on one or any combination of a correspondence between muscle efficiency and stride frequency, a correspondence between muscle tension and stride frequency, and other physiological states (e.g., risk of athletic injury) and a correspondence between stride frequency. At this time, the correspondence between the physiological state and the step frequency determined based on the various motion data such as the electromyographic signal, the posture signal, the electrocardiographic signal, the respiratory signal, and the like may be comprehensively considered, so that the recommended step frequency is determined.

In some embodiments, the recommended stride frequency may be determined based on a history of user motion. In some embodiments, the recommended stride frequency may be determined based on historical electromyographic signals. For example, the recommended stride frequency for the current user may be determined from a historical stride frequency corresponding to when muscle overfatigue is determined based on the historical electromyographic signals. For example only, the recommended stride frequency may be less than or slightly less than the historical stride frequency. For another example, the historical recommended stride frequency may also be combined with the current electromyographic signal to determine the recommended stride frequency of the current user.

In some embodiments, the recommended stride frequency may be determined in conjunction with the road environment (e.g., uphill, downhill) and the personal physical condition of the user (e.g., historical athletic records). For example, when a user runs on a sloped road section or a running machine, in order to prevent knee injury, the recommended step frequency of the sloped road section may be suitably smaller than the recommended step frequency of a gentle road section having the same physiological state. In some embodiments, when the system does not enter the real-time physical state or physical condition (e.g., road environment) of the user, the initial stride frequency (determined according to the historical exercise record of the user or determined according to the running data of other people) may be recommended to the user first, and after the user moves for a period of time under the initial stride frequency, the physiological state of the user is determined according to the exercise data in the period of time, and then the recommended stride frequency is determined according to the physiological state.

And step 340, feeding back the recommended step frequency to the user.

In some embodiments, step 340 may be performed by feedback module 240. In some embodiments, after determining the recommended stride frequency of the user based on the foregoing steps 310, 320, and 330, the recommended stride frequency may be further fed back to the user, and the user may adjust the stride frequency thereof according to the recommended stride frequency until the same as the recommended stride frequency, thereby improving the exercise efficiency.

In some embodiments, the same beat as the recommended stride frequency may be fed back to the user based on a preset feedback manner. The user adjusts his own stride frequency according to the recommended stride frequency so that the stride frequency is the same as the recommended stride frequency, after which the user may run at the recommended stride frequency. In some embodiments, the preset feedback mode may include at least one of voice feedback, vibration feedback, light feedback, and display feedback. In some embodiments, the same beats as the recommended step frequency may be fed back to the user based on a voice feedback approach. For example, a device (e.g., a cell phone, a watch, a headset) with a sound output function in a athletic data processing system may play the same voice beat as the recommended stride frequency, and the user adjusts his or her stride frequency based on the voice beat so that the stride frequency is the same or substantially the same as the recommended stride frequency. In some embodiments, the same beat as the recommended stride frequency may be fed back to the user based on a vibration feedback approach. For example, devices capable of generating vibrations in a athletic data processing system (e.g., cell phone, watch) may vibrate according to a recommended stride frequency. In some embodiments, the same beat as the recommended stride frequency may be fed back to the user based on a light feedback approach. For example, an electronic device (e.g., a cell phone, a watch) in the athletic data processing system may perform light flashes at the same frequency as the recommended stride frequency. In some embodiments, the same beat as the recommended stride frequency may be fed back to the user based on a display feedback manner. For example, an electronic device (e.g., a cell phone) in the athletic data processing system may display the recommended stride frequency.

In some embodiments, the recommended step frequency may be fed back to the user through a virtual reality device and/or an augmented reality device (e.g., AR glasses). For example, the user may wear AR glasses during running, the recommended stride frequency may be displayed in the AR glasses in the form of data, and the user adjusts his stride frequency according to the data of the recommended stride frequency. The recommended step frequency is fed back to the user through the AR glasses, so that the user can learn the recommended step frequency more clearly, meanwhile, the dependence of the user on a mobile phone, a watch and a bracelet can be reduced, and the physical burden of the user during running is reduced.

In some embodiments, the recommended step frequency may also be fed back to the user based on a biofeedback approach (e.g., electrical stimulation). In some embodiments, the stimulation may be applied to the body part of the user based on a biofeedback manner to feedback the recommended stride frequency to the user, wherein the stimulation applied to the body part of the user may have a stimulation frequency that is the same as the recommended stride frequency. In some embodiments, electrodes may be provided on a wearing body (e.g., a coat, pants, waistband, etc.) of the wearable device, which contact human skin when the user wears the wearable device. The processing device may control the electrodes to stimulate the body part of the user based on the stimulation frequency (i.e. the recommended step frequency).

The user adjusts the real-time step frequency according to the recommended step frequency, so that the real-time step frequency is consistent with the recommended step frequency and runs under the recommended step frequency, and the user can exercise in a more scientific and efficient mode, thereby improving the exercise efficiency.

It should be noted that the above description of the process 300 is for purposes of example and illustration only and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of the present description. For example, the motion data of the user is not limited to the electromyographic signals, the posture signals and the electrocardiosignals, but may be other physiological parameter signals, such as a temperature signal, a humidity signal, an oxygen concentration, a respiratory rate and the like, and the physiological parameter signals involved in the motion of the human body can be regarded as the motion data in the embodiments of the present specification. For another example, step 340 may be omitted. However, such modifications and variations are still within the scope of the present description.

Fig. 4 is an exemplary flow chart of a method of acquiring athletic data, according to some embodiments of the disclosure. In some embodiments, the flow 400 may be performed by the acquisition module 210. The process 400 may include:

step 410, acquiring real-time step frequency and real-time motion data of the user.

In some embodiments, the acquisition module 210 may acquire real-time stride frequency and real-time athletic data of the user while the user is running wearing the wearable device. In some embodiments, the user's real-time stride frequency may vary during different periods of time during running. For example, the real-time step frequency may have a tendency to gradually rise or fall. For example only, the real-time stride frequency of the user may be high upon starting running; after running for a period of time, the real-time step frequency is gradually reduced. For another example, the real-time stride frequency of the user may be time-high and time-low. Therefore, the motion data generated by running of the user under different real-time step frequencies, namely the real-time motion data corresponding to the real-time step frequencies are also different, and at the moment, the real-time step frequencies and the real-time motion data of the user can be obtained.

In some embodiments, the real-time step frequency may be obtained by a data acquisition device. In some embodiments, the real-time step frequency may be obtained by an inertial sensor. By way of example only, running motion is periodic, which is made up of a plurality of running motions periodically repeated, and the signals acquired by the inertial sensors (e.g., attitude sensors) also correspond to periodic signals (or similar periodic signals), and the user completing one running motion may be considered to complete one periodic motion, thereby enabling real-time stride frequency acquisition based on the inertial sensors. In some embodiments, the real-time step frequency may also be extracted from the electromyographic signal. For example, when a user runs, a periodic running motion may produce a periodically varying electromyographic signal. By extracting the period of the electromyographic signals, the real-time step frequency can be obtained.

Step 420, dividing the real-time step frequency into a plurality of step frequency intervals.

In some embodiments, the real-time step frequency may be divided into a plurality of step frequency intervals according to a plurality of step frequency ranges, each step frequency interval corresponding to one step frequency range. For example, the plurality of step frequency ranges may include 150 steps/min-160 steps/min, 160 steps/min-170 steps/min, 170 steps/min-180 steps/min, 180 steps/min-190 steps/min, 200 steps/min-210 steps/min, and the real-time step frequency is divided into corresponding 5 step frequency intervals according to the step frequency ranges. Each step frequency interval has a corresponding step frequency. That is, the step frequency of the first step frequency interval is between 140 steps/min and 150 steps/min, … … steps/min, and the step frequency of the fifth step frequency interval is between 200 steps/min and 210 steps/min. In some embodiments, to ensure that the difference in real-time motion data within a single step frequency interval is small, to ensure accuracy of motion data at unsynchronized frequencies, the step frequency range may be set small. In some embodiments, the difference between the upper and lower limits of the step frequency range may be less than 10 (steps/min). In some embodiments, the difference between the upper and lower limits of the preset range may be less than 8. In some embodiments, the difference between the upper and lower limits of the preset range may be less than 6. In some embodiments, the difference between the upper and lower limits of the preset range may be less than 5. In some embodiments, the difference between the upper and lower limits of the preset range may be less than 3. In some embodiments, the preset range may be set according to actual requirements, which is not specifically limited in the embodiments of the present disclosure.

Step 430, determining the motion data in the asynchronous frequency interval from the real-time motion data based on the step frequency interval.

In some embodiments, the real-time motion data at different real-time stride frequencies is different. For example, when the change of the real-time step frequency is large, the change of the real-time motion data is also large; the change of the real-time step frequency is smaller, and the change of the real-time motion data is smaller. In some embodiments, motion data corresponding to a step frequency interval may be determined from different step frequency intervals. For example, at least a part of the real-time motion data corresponding to the same step frequency interval may be collected as the motion data corresponding to the step frequency interval. For example only, the movement speed corresponding to the real-time stride frequency may or may not be within the target speed interval (i.e., the movement speed of the user may or may not be within the target speed interval when the data acquisition device acquires the real-time stride frequency). When the motion speeds corresponding to the real-time step frequency are all located in the target speed interval, the real-time motion data corresponding to the same step frequency interval can be collected to be used as the motion data corresponding to the step frequency interval. When the motion speed part corresponding to the real-time step frequency is positioned in the target speed interval, the real-time step frequency corresponding to the motion speed in the target speed interval can be screened out, and then the real-time motion data corresponding to the screened real-time step frequency positioned in the same step frequency interval is collected to be used as the motion data corresponding to the step frequency interval.

In some embodiments, the method of acquiring motion data based on real-time stride frequency may have greater flexibility than acquiring motion data based on preset stride frequency. The method is characterized in that when the motion data are acquired based on the preset step frequency, the step frequency is required to be kept in a preset step frequency interval by a user, and if the step frequency of the user exceeds the preset step frequency interval, the accuracy of the motion data is affected; the step frequency of the user does not need to be controlled when the motion data is acquired based on the real-time step frequency, and the user can freely do motion with unsynchronized frequency.

It should be noted that the above description of the process 400 is for purposes of illustration and description only, and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 400 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description.

FIG. 5 is an exemplary flow chart for determining recommended stride frequency according to some embodiments of the present description. In some embodiments, the process 500 may be performed by the determination module 220. The process 500 may include:

Step 510, determining a correspondence between the physiological state of the user and step frequency based on the electrocardiographic signal and/or the posture signal.

In some embodiments, the physiological state of the user may also include a risk of athletic injury. During running, a user may not only fail to achieve the desired exercise efficiency, but may also cause injury to the human body due to wrong exercise, such as a wrong running posture, improper running stride frequency, too fast heart rate, etc. In some embodiments, the risk of athletic injury may include a risk of gesture injury. The risk of pose damage may include damage errors, compensation errors, efficiency errors, symmetry errors, and the like, or any combination thereof. A damage error may mean that the exercise error may cause damage to the human body. Compensation errors may refer to errors that assist in developing forces using non-target sites (e.g., knees, ankles). An efficiency error may refer to a swing arm or stride having too large or too small a range of motion to allow the target site to be at a non-optimal level of activation. A symmetry error may refer to a situation where two symmetrical (e.g., bilateral, anteroposterior symmetrical) locations on the human body are unbalanced in force. In some embodiments, the athletic injury risk may include an injury grade. For example only, the injury risk level may include severe, moderate, mild, etc.

In some embodiments, a risk of athletic injury to the user may be determined based on the gesture signal. The posture signal may include information such as an angle, a speed, and an acceleration of each joint, or an euler angle, an angular speed, and an angular acceleration of each human body part. In some embodiments, the gesture signal may be used to characterize the technical accuracy of the user's current motion (e.g., joint angle, force sequence, etc.), thereby determining the risk of motion injury (e.g., knee injury, ankle injury). In some embodiments, the gesture signal may be acquired by a gesture signal acquisition device. Exemplary gesture signal acquisition devices may include a speed sensor, an inertial sensor (e.g., acceleration sensor, angular velocity sensor (e.g., gyroscope), etc.), an optical sensor (e.g., optical distance sensor, video/image acquisition), an acoustic distance sensor, a tension sensor, etc., or any combination thereof.

In some embodiments, the risk of athletic injury may include a risk of cardiac injury. As the step frequency increases, the heart rate of the user may gradually increase, and when the heart rate is higher than the threshold heart rate, a risk of heart damage may occur. In some embodiments, the risk of cardiac injury to the user may be determined based on the cardiac signal. An electrocardiograph signal may refer to a signal that is representative of the heart activity of a user. In some embodiments, the electrocardiograph signal may be acquired by an electrocardiograph signal acquisition device. For example, the electrocardiographic signal acquisition device may include a plurality of electrodes that may be used to conform to different portions of the subject to be evaluated (e.g., by) to acquire electrocardiographic signals of the subject to be evaluated.

In some embodiments, the correspondence between physiological states and step frequencies, which is determined based on the electrocardiographic and/or posture signals, may also be referred to as a second correspondence. The second correspondence may include a correspondence between risk of gesture damage and step frequency. In some embodiments, a correspondence between the risk of gesture damage and a plurality of preset step frequencies may be determined. In some embodiments, the gesture signal at the first preset step frequency may be processed (e.g., processed by using a feature value) to obtain a gesture damage risk (denoted as a first gesture damage risk) at the first preset step frequency, so as to determine a correspondence between the first preset step frequency and the first gesture damage risk. That is, the first risk of gesture damage corresponds to a first preset step frequency. Similarly, a corresponding relationship between the second preset step frequency and the second gesture damage risk, a corresponding relationship between the third preset step frequency and the third gesture damage risk, … …, and a corresponding relationship between the Nth preset step frequency and the Nth gesture damage risk can be determined. In some embodiments, a correspondence between risk of gesture damage and real-time stride frequency may also be determined.

In some embodiments, the second correspondence may include a correspondence between cardiac injury risk and step frequency. In some embodiments, a correspondence between cardiac injury risk and step frequency of the user may be determined based on the electrocardiographic signals. In some embodiments, a correspondence between the risk of cardiac injury and a plurality of preset step frequencies may be determined. In some embodiments, the cardiac signal at the first preset step frequency may be processed to obtain a cardiac injury risk (denoted as a first cardiac injury risk) at the first preset step frequency, i.e. the first cardiac injury risk corresponds to the first preset step frequency. Similarly, a correspondence between the second preset step frequency and the second cardiac injury risk, a correspondence between the third preset step frequency and the third cardiac injury risk, … …, and a correspondence between the nth preset step frequency and the nth cardiac injury risk may be determined. In some embodiments, a correspondence between cardiac injury risk and real-time step frequency may also be determined.

Step 520, determining the recommended step frequency of the user based on the correspondence.

In some embodiments, the recommended stride frequency of the user may be determined based on a correspondence between the risk of athletic injury and the stride frequency. For example, the stride frequency at which the risk of athletic injury is lowest may be determined as the recommended stride frequency. In some embodiments, one step frequency may be determined from the unsynchronized frequencies as the recommended step frequency based on a correspondence between risk of gesture motion injury and step frequency. In some embodiments, one step frequency may be determined from the unsynchronized frequencies as a recommended step frequency based on a correspondence between cardiac injury risk and step frequency.

It should be noted that, in other embodiments, the recommended step frequency of the user may also be determined in combination with other motion data, such as a correspondence between a physiological state determined by a respiratory signal, a pressure signal, a sweat signal, etc. and a step frequency.

In some embodiments, the user runs with a breathing rhythm, e.g., a few steps to one breath. The breathing rhythm of the user can also influence the physiological state of the user. In some embodiments, a strain sensor (or contact resistance) may be disposed on a waistband of the wearable device, and when a user breathes, the dimension of the waist and abdomen changes, and a signal value acquired by the strain sensor also changes. In some embodiments, the breathing rate of the user during running can be detected by the strain sensor, and the breathing rhythm is adjusted according to the breathing rate, so that the user can be helped to perform more scientific exercise.

It should be noted that the above description of the process 500 is for purposes of illustration and description only, and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 500 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description.

FIG. 6 is an exemplary flow chart of a feedback recommended stride method according to some embodiments of the present description. In some embodiments, the process 600 may be performed by the recommendation module 240. The process 600 may include:

step 610, obtaining a real-time step frequency of the user.

In some embodiments, the real-time stride frequency may refer to a stride frequency at a current time during a user's running. In some embodiments, the real-time step frequency may be obtained by a data acquisition device. In some embodiments, the real-time step frequency may be obtained by an inertial sensor. For more details regarding the manner in which the step frequency is acquired by the data acquisition device, see, for example, fig. 4 and its associated description, which are not repeated herein.

Step 620, determining a step frequency adjustment trend of the user based on the frequency difference between the real-time step frequency and the recommended step frequency.

In some embodiments, the user's real-time stride frequency typically has a frequency difference with the recommended stride frequency. For example, when the real-time step frequency of the user is larger and the real-time step frequency is larger than the recommended step frequency, the frequency difference between the real-time step frequency and the recommended step frequency is positive. For another example, the real-time step frequency of the user is smaller, and when the real-time step frequency is smaller than the recommended step frequency, the frequency difference between the real-time step frequency and the recommended step frequency is negative. In some embodiments, the step frequency adjustment trend may include a frequency decrease trend and a frequency increase trend. When the frequency difference between the real-time step frequency and the recommended step frequency is positive, determining that the step frequency adjustment trend of the user is a frequency reduction trend; when the frequency difference between the real-time step frequency and the recommended step frequency is negative, the step frequency adjustment trend of the user can be determined to be a frequency increasing trend. In some embodiments, the step frequency adjustment trend may also include a frequency invariant, where the real-time step frequency is the same as the recommended step frequency.

Step 630, guiding the user based on the step frequency adjustment trend until the step frequency of the user is the same as the recommended step frequency.

In some embodiments, the user may adjust his or her own real-time stride frequency based on the recommended stride frequency such that the real-time stride frequency is the same as the recommended stride frequency. In some embodiments, when the step frequency adjustment trend is a frequency reduction trend, the user may be guided to gradually reduce the real-time step frequency of the user until the real-time step frequency is the same as the recommended step frequency; when the step frequency adjustment trend is a frequency increasing trend, the user can be guided to gradually increase the real-time step frequency until the real-time step frequency is the same as the recommended step frequency. In some embodiments, when the step frequency adjustment trend is that the frequency is unchanged, the real-time step frequency is the same as the recommended step frequency, and the user does not need to adjust the step frequency.

In some embodiments, when the user is guided to adjust the step frequency based on the step frequency adjustment trend, the dynamic beat with gradually changing frequency can be fed back to the user based on feedback modes (e.g., voice feedback, vibration feedback, light feedback, display feedback, biofeedback modes, etc.). The frequency change trend of the dynamic beat is the same as the step frequency adjustment trend. For example, when the step frequency adjustment trend is a frequency reduction trend, the starting frequency of the dynamic beat is the real-time step frequency of the user, the target frequency of the dynamic beat is the recommended step frequency, and the frequency of the dynamic beat gradually decreases from the starting frequency to the target frequency. For another example, when the step frequency adjustment trend is a frequency increasing trend, the starting frequency of the dynamic beat is the real-time step frequency of the user, the target frequency of the dynamic beat is the recommended step frequency, and the frequency of the dynamic beat gradually increases from the starting frequency to the target frequency. In some embodiments, the frequency adjustment process of the dynamic beat may be uniformly varied. In some embodiments, the frequency adjustment process of the dynamic beat may also be unevenly varied.

The step frequency adjusting trend based mode for guiding the user to adjust the step frequency can enable the step frequency adjusting process of the user to be more scientific and healthy.

It should be noted that the above description of the process 600 is for purposes of example and illustration only and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 600 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description.

In some embodiments, the recommended stride frequency described in embodiments of the present disclosure may be adjusted in real time based on the state of the user during running. In some embodiments, the user adjusts his own stride frequency based on the recommended stride frequency such that after the stride frequency is the same as the recommended stride frequency, the user may remain running at the recommended stride frequency. When running is performed under the recommended step frequency, the data acquisition device can continuously acquire the motion data of the user. When the user runs for a certain time with the recommended step frequency, and the exercise data collected by the data collection device indicate that the physiological state of the user can be improved continuously, the recommended step frequency can be adjusted or the recommended step frequency can be determined again according to the current physiological state of the user. For example, when the current physiological state of the user is good and there is room for improvement, for example, the muscle is not in a fatigue state, the muscle efficiency can be improved, which indicates that the step frequency of the user can be improved on the basis of the recommended step frequency, and at this time, the recommended step frequency can be redetermined or updated according to the current physiological state of the user. For another example, the current physiological state of the user is poor, e.g., the heart rate is too fast, the muscles are in a fatigued state for a long time, indicating that the stride frequency of the user can be reduced on the basis of the recommended stride frequency, at which time the recommended stride frequency can be redetermined or updated according to the current physiological state of the user. The recommended step frequency can be adjusted in real time, so that the exercise efficiency of the user in the running exercise process can be further improved.

As can be seen from the above description, the motion data processing method described in fig. 3 to 6 determines the physiological state of the user based on the motion data of the user under the unsynchronized frequency, and then determines the recommended step frequency of the user based on the physiological state. In some embodiments, in order to reduce the time of motion data processing and calculation, so as to more quickly determine the recommended step frequency of the user, the step of determining the physiological state may be omitted, and the recommended step frequency of the user is directly determined according to the motion data, so that the user can learn the recommended step frequency of the user in a shorter time, thereby further improving the motion efficiency.

In some embodiments, a recommended stride frequency for the user may be determined based on the motion data. In some embodiments, the recommended stride frequency of the user may be determined based on a stride frequency recommendation model. In some embodiments, the input of the stride frequency recommendation model may include, but is not limited to, various types of motion data at a preset stride frequency, such as one or any combination of electromyographic signals, posture signals, electrocardiographic signals, respiratory signals, pressure signals, and the like. The output of the stride frequency recommendation model may be a recommended stride frequency. In some embodiments, the stride frequency recommendation model may be a trained machine learning model. In some embodiments, the step frequency recommendation model may be trained beforehand by the processing device and stored in the storage device, which the processing device may access to obtain the step frequency recommendation model.

In some embodiments, the step frequency recommendation model may be trained based on sample information. The sample information may include exercise data for a professional (e.g., fitness trainer) and/or non-professional exercise. In some embodiments, the sample information may also include historical motion data of the user himself. For example, after wearing the wearable device, the user performs running exercises with different step frequencies for a plurality of times, and the exercise data can be used as historical exercise data by using the data acquisition device. When the motion data is taken as sample information, the physiological state of the user can be monitored while the motion data is acquired. In some embodiments, the motion data in the sample information may be processed (e.g., segmented, burred, and transform processed, etc.) signals. In some embodiments, the motion data may be used as input to a machine learning model to train the machine learning model. In some embodiments, the feature information corresponding to the motion data may also be used as an input to a machine learning model to train the machine learning model. For example, frequency information and amplitude information of the electromyographic signals may be used as inputs to a machine learning model. For another example, the angular velocity of the attitude signal, the angular velocity direction, and the acceleration value of the angular velocity may be used as inputs to the machine learning model. In some embodiments, the machine learning model may include one or more of a linear classification model (LR), a support vector machine model (SVM), a naive bayes model (NB), a K-nearest neighbor model (KNN), a decision tree model (DT), an integrated model (RF/GDBT, etc.), and the like. In some embodiments, sample information of different motion data may be labeled as the machine learning model is trained. Taking the motion data as an electromyographic signal as an example, the electromyographic signal generated by the user moving at the first step frequency can be marked as a 'first step frequency'; the electromyographic signal produced by the user's motion at the second step frequency may be labeled "second step frequency". The physiological states corresponding to different electromyographic signals are different, the labeled sample information (namely, each electromyographic signal labeled) is used as the input of a machine learning model to train the machine learning model, a step frequency recommendation model for determining the recommended step frequency can be obtained, and the corresponding recommended step frequency can be output when the motion data and/or the corresponding characteristic information are input into the machine learning model.

In some embodiments, the user's movement speed may be the same when obtaining sample information (i.e., movement data at unsynchronized frequencies) used to train the machine learning model. In some embodiments, the user's movement speed may also be different when obtaining sample information (i.e., movement data at unsynchronized frequencies) used to train the machine learning model. At this time, the motion speed can be monitored while the motion data is acquired, and the influence caused by the difference of the motion speeds can be compensated in the later data processing process.

In some embodiments, to improve the accuracy of the recommended stride frequency, the processing device may determine the recommended stride frequency of the user based on two or more of the signals of the gesture signal, the electromyographic signal, the mechanical signal, the cardiac signal, the respiratory signal, the sweat signal, and the like. That is, one or more of the posture signal, the electromyographic signal, the mechanical signal, the electrocardiographic signal, the respiratory signal, the sweat signal, etc., and the movement speed of the user can be used as the input of the machine learning model to train the machine learning model, so that the recommended step frequency output by the machine learning model is more suitable for the user. In some embodiments, in practical application, the recommended step frequency (also called initial recommended step frequency) under the target training task can be estimated according to the information input by the user, the user moves with the initial recommended step frequency, the actual movement data of the user can be collected in the movement process, and the movement data processing system can iteratively update the step frequency recommendation model according to the actual movement data, so that the recommended step frequency output by the step frequency recommendation model is more accurate. In some embodiments, during long-term use by the user, the athletic data processing system may collect more athletic data, thereby making the recommended pace recommended by the athletic data processing system more reasonable.

In some embodiments, the present description embodiments also provide a wearable device. The wearable device can comprise a wearing body, wherein the wearing body is provided with at least one sensor for acquiring motion data of a user; and a processor capable of performing the method of motion data processing described in fig. 3-6. In some embodiments, the wearing body may include, but is not limited to, one or more of a coat, pants, waistband, sock, knee pad, wrist band, and the like. The sensors may include one or more of a myoelectric sensor (one or more electrodes), an attitude sensor (e.g., a speed sensor, an inertial sensor, an angular velocity sensor, etc.), a pressure sensor, and the like. When the user wears the wearable device and runs, the sensor is in contact with the body part of the user, so that movement data of the user during movement can be acquired. For example, the electromyographic sensor may include one or more electrodes that, when positioned in the wearable device corresponding to a muscle site of the human body, may collect electromyographic signals of the muscle at the corresponding site. For another example, one or more electrodes may be positioned on the wearable device corresponding to the abdomen of a person to collect electrocardiographic signals (or respiratory signals) of the user while the user is in motion. For another example, an attitude sensor located at a position of the wearable device corresponding to a joint portion of the human body, such as a knee joint, an elbow joint, an ankle joint, may collect an attitude signal when the user moves. For more on the wearable device and the method of processing motion data performed by the processor, see the relevant description of fig. 1-6.

In some embodiments, the stimulation may also be applied to a body part of the user using electrodes provided on the wearing body that are in contact with the skin of the user. In some embodiments, the electrodes may be used to stimulate a body part of the user to feed back recommended stride frequency to the user. In some embodiments, the frequency at which the electrodes stimulate the body part (i.e., the stimulation frequency) may be the same as the recommended stride frequency, and the user adjusts the real-time stride frequency based on the stimulation received by the body until the stride frequency is the same as the stimulation frequency. In some embodiments, the electrodes may also stimulate the user's body part at a dynamic stimulation frequency that varies in the same manner as the user's step frequency adjustment. For example, when the trend of step frequency adjustment is a trend of frequency decrease, the starting frequency of the dynamic stimulus frequency may be a real-time step frequency of the user, the target frequency of the dynamic stimulus frequency is a recommended step frequency, and the dynamic stimulus frequency is gradually reduced from the starting frequency to the target frequency. In some embodiments, the adjustment process of the dynamic stimulation frequency may be uniformly varied. In some embodiments, the adjustment process of the dynamic stimulation frequency may also be unevenly varied.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application is not intended to limit the sequence of the processes and methods unless specifically recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of example, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing processing device or mobile device.

Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject application requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations in some embodiments for use in determining the breadth of the range, in particular embodiments, the numerical values set forth herein are as precisely as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited herein is hereby incorporated by reference in its entirety. Except for the application history file that is inconsistent or conflicting with this disclosure, the file (currently or later attached to this disclosure) that limits the broadest scope of the claims of this disclosure is also excluded. It is noted that the description, definition, and/or use of the term in the appended claims controls the description, definition, and/or use of the term in this application if there is a discrepancy or conflict between the description, definition, and/or use of the term in the appended claims.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the application may be considered in keeping with the teachings of the application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly described and depicted herein.

Claims (15)

1. A method of motion data processing, comprising:

acquiring motion data of a user under asynchronous frequency, wherein the motion data at least comprises electromyographic signals;

determining a physiological state of the user based on the motion data; and

A recommended stride frequency of the user is determined based on the physiological state.

2. The method of claim 1, wherein the acquiring motion data of the user at the unsynchronized frequency comprises:

Determining a target speed interval;

And acquiring motion data in the asynchronous frequency in the target speed interval based on the target speed interval.

3. The method of claim 1, wherein the physiological state includes muscle efficiency, muscle tension, and muscle fatigue, the determining a recommended stride frequency of the user based on the physiological state comprising:

Determining a correspondence between the physiological state of the user and a step frequency based on at least one of the muscle efficiency, the muscle tension, and the muscle fatigue; and

And determining the recommended step frequency of the user based on the corresponding relation.

4. A method according to claim 3, wherein the determining the physiological state of the user based on the motion data comprises:

At least one of the muscle efficiency, the muscle tension, and the muscle fatigue of the user is determined based on the electromyographic signal.

5. The method of claim 1, wherein the motion data comprises an electrocardiographic signal and/or a gesture signal, the determining a recommended stride frequency of the user based on the physiological state comprising:

Based on the electrocardiosignal and/or the gesture signal, determining a corresponding relation between the physiological state and step frequency of the user; and

And determining the recommended step frequency of the user based on the corresponding relation.

6. The method of claim 5, wherein the determining the physiological state of the user based on the motion data comprises:

A physiological state of the user is determined based on the electrocardiographic and/or posture signals, the physiological state comprising a risk of injury to the user's movement.

7. The method of claim 1, wherein the acquiring motion data of the user at the unsynchronized frequency comprises:

Acquiring real-time step frequency and real-time motion data of the user;

dividing the real-time step frequency into a plurality of step frequency intervals;

Determining the motion data in an asynchronous frequency interval from the real-time motion data based on the step frequency interval; the real-time step frequency is obtained through an inertial sensor or is obtained from the electromyographic signals.

8. The method of claim 1, wherein the method further comprises: and feeding back the recommended step frequency to the user.

9. The method of claim 8, wherein the feeding back the recommended stride frequency to the user comprises:

acquiring the real-time step frequency of the user;

Determining a step frequency adjustment trend of the user based on the frequency difference between the real-time step frequency and the recommended step frequency;

and guiding the user based on the step frequency adjustment trend until the step frequency of the user is the same as the recommended step frequency.

10. The method of claim 8, wherein the feeding back the recommended stride frequency to the user comprises:

feeding back beats which are the same as the recommended step frequency to the user based on a preset feedback mode; the preset feedback mode comprises at least one of voice feedback, vibration feedback, lamplight feedback and display feedback.

11. The method of claim 8, wherein the feeding back the recommended stride frequency to the user comprises:

And stimulating the body part of the user based on a biofeedback mode to feed back the recommended step frequency to the user, wherein the stimulation has a stimulation frequency which is the same as the recommended step frequency.

12. The method of claim 1, wherein the acquiring motion data of the user at the unsynchronized frequency comprises:

And acquiring multiple sets of motion data of the user under multiple preset step frequencies, wherein each set of motion data corresponds to one of the multiple preset step frequencies.

13. The method of claim 12, wherein the acquiring multiple sets of motion data for the user at multiple preset step frequencies comprises:

acquiring physiological information of the user, wherein the physiological information comprises body information and motion information;

and determining the plurality of sets of motion data of the user at the plurality of preset step frequencies based on the physiological information.

14. A athletic data processing system, comprising:

the acquisition module is used for acquiring motion data of a user under asynchronous frequency, wherein the motion data at least comprises an electromyographic signal;

A processing module for determining a physiological state of the user based on the motion data;

And the recommending module is used for determining the recommending step frequency of the user based on the physiological state.

15. A wearable device, comprising:

The wearable device comprises a wearable body, wherein the wearable body is provided with at least one sensor, and the sensor is used for acquiring motion data of a user; and

A processor configured to perform the method of any one of claims 1-13.